mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
1f83b5f47e
This PR changes the behavior of `Qdrant.from_texts` so the collection is reused if not requested to recreate it. Previously, calling `Qdrant.from_texts` or `Qdrant.from_documents` resulted in removing the old data which was confusing for many.
80 lines
2.9 KiB
Python
80 lines
2.9 KiB
Python
"""Fake Embedding class for testing purposes."""
|
|
import math
|
|
from typing import List
|
|
|
|
from langchain.embeddings.base import Embeddings
|
|
|
|
fake_texts = ["foo", "bar", "baz"]
|
|
|
|
|
|
class FakeEmbeddings(Embeddings):
|
|
"""Fake embeddings functionality for testing."""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return simple embeddings.
|
|
Embeddings encode each text as its index."""
|
|
return [[float(1.0)] * 9 + [float(i)] for i in range(len(texts))]
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return constant query embeddings.
|
|
Embeddings are identical to embed_documents(texts)[0].
|
|
Distance to each text will be that text's index,
|
|
as it was passed to embed_documents."""
|
|
return [float(1.0)] * 9 + [float(0.0)]
|
|
|
|
|
|
class ConsistentFakeEmbeddings(FakeEmbeddings):
|
|
"""Fake embeddings which remember all the texts seen so far to return consistent
|
|
vectors for the same texts."""
|
|
|
|
def __init__(self, dimensionality: int = 10) -> None:
|
|
self.known_texts: List[str] = []
|
|
self.dimensionality = dimensionality
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return consistent embeddings for each text seen so far."""
|
|
out_vectors = []
|
|
for text in texts:
|
|
if text not in self.known_texts:
|
|
self.known_texts.append(text)
|
|
vector = [float(1.0)] * (self.dimensionality - 1) + [
|
|
float(self.known_texts.index(text))
|
|
]
|
|
out_vectors.append(vector)
|
|
return out_vectors
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return consistent embeddings for the text, if seen before, or a constant
|
|
one if the text is unknown."""
|
|
if text not in self.known_texts:
|
|
return [float(1.0)] * (self.dimensionality - 1) + [float(0.0)]
|
|
return [float(1.0)] * (self.dimensionality - 1) + [
|
|
float(self.known_texts.index(text))
|
|
]
|
|
|
|
|
|
class AngularTwoDimensionalEmbeddings(Embeddings):
|
|
"""
|
|
From angles (as strings in units of pi) to unit embedding vectors on a circle.
|
|
"""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""
|
|
Make a list of texts into a list of embedding vectors.
|
|
"""
|
|
return [self.embed_query(text) for text in texts]
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""
|
|
Convert input text to a 'vector' (list of floats).
|
|
If the text is a number, use it as the angle for the
|
|
unit vector in units of pi.
|
|
Any other input text becomes the singular result [0, 0] !
|
|
"""
|
|
try:
|
|
angle = float(text)
|
|
return [math.cos(angle * math.pi), math.sin(angle * math.pi)]
|
|
except ValueError:
|
|
# Assume: just test string, no attention is paid to values.
|
|
return [0.0, 0.0]
|